Der Shop ist online

Wir bauen Workstation AI-Maschinen für Websites, KI-Agenten und LLM-Training – online konfigurieren und kaufen.

Händlerpreise erhalten
KI-Produkte
KI-LabsOpenAI-AgentenClaude-AgentenGrok-BotWorkstation AI-natives CRMMarketingAlle Produkte
KI-Lösungen
Angewandte KIKI-AgentenGenerative KIKI-AutomatisierungKI-WeiterbildungKI-Pakete für KMUEnterprise AI LabKI-WorkstationsNVIDIA-Hardware & -SoftwareNVIDIA Accelerated ComputingPrivate KIGPU-Private-CloudGPU-ClusterEdge-KIKI nach Branche
KI-Services
PlattformmodernisierungDigital EngineeringDatengrundlagen & KIAutonomer BetriebKI-BeratungDevOps-AutomatisierungCybersicherheitSoftwareentwicklungAgentenentwicklungMLOps-EinrichtungGPU-LeasingGPU-Private-Cloud
Über uns
UnternehmenUnsere GeschichtePartnerKundengeschichten
KI-Rechenzentren
KI-RechenzentrenGPU-Private-CloudGPU-ClusterGPU-Leasing
KI-EinblickeJev-ReiheBenchmark LabModellauswahl
Technische Hinweise
Dokumentation
Linux-BetriebssystemeUbuntuRed Hat Enterprise LinuxSUSE LinuxAlpine LinuxDebian, Rocky & AlmaLinux
KI-Cloud-PlattformenAWS & Amazon BedrockGoogle Cloud & Vertex AIMicrosoft Azure & AI FoundryGPU-Clouds & Marktplätze
Private KI-RechenzentrenFür AnwaltskanzleienFür Steuer- und WirtschaftsprüfungskanzleienOn-Premises-PlattformenVollständig abgesicherte Cloud
ToolsRing PromoterJobshout
News
Blog
KontaktAnmelden

KI-Workstations, Multi-Agenten-KI-Software, GPU-Infrastruktur und intelligente Agentenlösungen für moderne Unternehmen.

Kontakt

KI-Lösungen

Angewandte KIKI-AgentenGenerative KIKI-AutomatisierungKI-WeiterbildungKI-Pakete für KMUEnterprise AI LabKI nach Branche

Produkte

Alle ProdukteWorkstation AI-natives CRM & ERPMarketingOpenAI-AgentenRing PromoterJobshout

Unternehmen

Über unsUnternehmenKI-RechenzentrenWarum WorkstationPartnerKundengeschichtenPreiseKontaktTenthMatrix

Ressourcen

KI-EinblickeTechnische HinweiseDokumentationLinux-BetriebssystemeKI-Cloud-PlattformenPrivate KI-RechenzentrenBlogSucheSitemap
Büro Belgien
Workstation SRL, Rue Vanderkindere 34, 1180 Uccle, BrusselsBE 0751.518.683Mo – Fr: 9:00 – 18:00 Uhr MEZ
+32 492 45 67 46
Hauptsitz Großbritannien
77-79 Marlowes, Hemel Hempstead HP1 1LFAnfahrt – Ausfahrt 20 der M25 (Outer London)Handelsregisternr.: 11641870Mo – Fr: 9:00 – 18:00 Uhr GMT
+44 7515 356 146
Büro Indien
#159 Sector 9, Pocket 1, DDA Flats, 110077 Dwarka, New Delhi
+91 98881 98841
Büro Taiwan
3F, No. 2-4, Aisi Rd., Ren'ai Dist., Keelung City 200, Taiwan基隆市仁愛區愛四路2之4號3樓Mo – Fr: 9:00 – 18:00 Uhr Taiwan-Zeit (GMT+8)
+886 926 892 701+32 492 45 67 46
Büro Estland
Aleksander Puškini tn 30-25, 20306 Narva, EstoniaMo - Fr: 9:00 - 18:00 Uhr estnischer Zeit (EET)
+32 492 45 67 46

© 2026 Workstation AI. Alle Rechte vorbehalten.

DatenschutzDatenlöschungCookiesNutzungsbedingungenWebsite-Sitemap

NVIDIA, das NVIDIA-Logo, RTX, RTX PRO, Blackwell, CUDA, NVLink, MGX, Omniverse, Spectrum-X, Quantum, BlueField, DGX und HGX sind Marken und/oder eingetragene Marken der NVIDIA Corporation in den USA und anderen Ländern. AMD, das AMD-Arrow-Logo, EPYC, Instinct, Ryzen und Threadripper sind Marken von Advanced Micro Devices, Inc. Dell und PowerEdge sind Marken der Dell Inc. oder ihrer Tochtergesellschaften. Intel und Xeon sind Marken der Intel Corporation oder ihrer Tochtergesellschaften. AMAX, AceleMax und LiquidMax sind Marken der AMAX Engineering Corporation. Alle anderen Produktnamen, Logos und Marken sind Eigentum ihrer jeweiligen Inhaber. Wir verwenden sie ausschließlich, um die Produkte zu kennzeichnen, die wir beschreiben, liefern oder unterstützen; ihre Verwendung bedeutet nicht, dass ihre Inhaber uns empfehlen.

Jev & The Next Generation of AI Automation

Building a Jev agent harness

Workstation’s reference architecture for planners, fast decision layers, routers, tool gates and evaluators — inspired by public LangChain patterns, implemented as our own design.

Published 26 September 2026Updated 26 September 2026Reading time 20 minAI landscape reviewed 26 September 2026
Building a Jev agent harness

Key takeaways

  • Keep the planner generative; insert decision models at routing, safety and evaluation seams.
  • Middleware beats prompt-only policy for tool risk.
  • Record distributions, versions and gate outcomes for every decision.

Why this matters

Harnesses are where agents become software. The planner can be clever and still be unsafe, slow or bankrupt if every micro-decision is another frontier completion. LangChain’s public Jev post shows two concrete seams — model routing middleware and Auto Mode tool gating. Workstation generalises those seams into a full loop you can implement with Jev or with any calibrated decision backend.

Workstation original harness: planner → fast decisions → tools/models → evaluator.
Workstation original harness: planner → fast decisions → tools/models → evaluator.

Reference loop

  1. Ingest user request and memory/context.
  2. Planner (LLM/reasoning) proposes next action.
  3. Fast decision layer scores routing, risk and stop conditions.
  4. Execute tool or generative step.
  5. Observe results.
  6. Evaluator classifies healthy / retry / escalate / failed.
  7. Repeat with budget caps.

Fast decision layer responsibilities

SeamQuestion shapeAction
Model routingChoice over model tiersBind model for the run or step
Tool safetyNoul/Score on riskAllow / deny / escalate
Failure detectionChoice over health labelsRetry policy or handoff
RAG answerabilityNoul + Score on supportAnswer, abstain, retrieve more

Original Workstation sketch (TypeScript-ish)

type Gate = 'act' | 'review' | 'escalate'

async function safetyGate(toolCall, state): Promise<Gate> {
  const ans = await decisionModel.ask({
    state: { toolCall, transcripts: state.trace.slice(-6) },
    questions: {
      irreversible: { type: 'noul', instructions: 'Irreversible prod mutation?' },
      risk: { type: 'score', levels: ['low','medium','high','critical'] },
    },
  })
  if (ans.noul.irreversible > 0.8 || ans.score.risk >= 3) return 'escalate'
  if (ans.confidence < 0.65) return 'review'
  return 'act'
}
Independence

This is Workstation sample logic. It is not a copy of LangChain AutoModeMiddleware source, and it is not an official TypeSafe cookbook.

Observability

Emit OpenTelemetry spans for each decision with attributes: model_version, question_ids, latency_ms, network_ms, argmax, confidence, gate_result, benchmark_suite_version. Without that, you cannot debug silent policy drift when jev-latest moves.

Limitations

A harness cannot invent ground truth. If your safety labels are wrong, a fast model will reliably enforce the wrong policy. Start with synthetic + shadowed production traces before enforcing denies.

Extended implementation notes

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 1: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 2: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 3: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 4: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 5: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 6: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 7: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 8: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 9: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 10: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 11: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 12: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 13: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 14: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 15: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 16: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 17: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Additional engineering context for Building a Jev agent harness: treat every automation seam as a product surface with owners, SLOs and offline labels. When integrating decision models, log versioned model ids, criteria hashes and gate outcomes. Compare against fast LLMs and reasoning LLMs on the same items before standardising. Cite TypeSafe or LangChain when repeating their claims; cite OpenRouter, AyAutomate, LangSmith or JevBench when using their numbers; never present those numbers as Workstation measurements. Connect this page to the Benchmark Lab and Model Selection Manual for next actions. Note cluster 18: prefer shadow mode, then canary, then enforce. Re-evaluate after each model alias move.

Conclusion

The harness is the product. Jev is one possible engine for the decision seams. The architecture remains valuable even if you swap engines.

Related on Workstation

  • AI Agents
  • Benchmark lab
  • Model selection
  • Jobs
  • Applied AI

Sources

  1. TypeSafe AI — Introducing System One Models & Jev — Vendor announcement.
  2. LangChain — Building a Harness with Jev — Harness patterns.
  3. TypeSafe docs index — Official primitives and API.
  4. LangChain — Jev as agent evaluator — Judge variance experiment.
  5. OpenRouter — Jev vs LLM — Triage tables.
  6. AyAutomate independent benchmark — 791 decisions.
  7. JevBench RESULTS — Public harness.
  8. OpenAI — Introducing the Agents API — Agent platform context in the wider landscape.

Ask about this article

Curated answers from this page's sources and methodology. Not a live model call.

How do I implement this in Rust?Model the gate as a pure function over DecisionResponse → Enum, call the HTTP System One API with reqwest, and keep criteria in versioned config. Unofficial crates like jev-sdk exist; prefer official SDKs when available for your stack.

On this page

  1. Why this matters
  2. Reference loop
  3. Fast decision layer responsibilities
  4. Original Workstation sketch (TypeScript-ish)
  5. Observability
  6. Limitations
  7. Extended implementation notes
  8. Conclusion
  9. Sources

Explore

  1. AI Insights home
  2. Jev series
  3. Benchmark lab
  4. AI Agents
  5. Jobs